Skip to content

Commit

Permalink
fix typo
Browse files Browse the repository at this point in the history
  • Loading branch information
mirceamironenco committed Nov 7, 2024
1 parent c00aea7 commit 88334e6
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion torchtune/modules/kv_cache.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ class KVCache(nn.Module):
Args:
batch_size (int): batch size model will be run with
max_seq_len (int): maximum sequence length model will be run with
num_kv_heads (int): number key/value heads.
num_kv_heads (int): number of key/value heads.
head_dim (int): per-attention head embedding dimension
dtype (torch.dtype): dtype for the caches
"""
Expand Down

0 comments on commit 88334e6

Please sign in to comment.